Instructions to use episod/tt-tnt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use episod/tt-tnt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="episod/tt-tnt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("episod/tt-tnt")
model = AutoModelForCausalLM.from_pretrained("episod/tt-tnt", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use episod/tt-tnt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "episod/tt-tnt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "episod/tt-tnt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/episod/tt-tnt

SGLang

How to use episod/tt-tnt with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "episod/tt-tnt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "episod/tt-tnt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "episod/tt-tnt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "episod/tt-tnt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use episod/tt-tnt with Docker Model Runner:
```
docker model run hf.co/episod/tt-tnt
```

episod commited on 23 days ago

Commit

5c560e1

verified ·

1 Parent(s): fd37c60

tokenizer_config: plain continuation chat template (the trained format; no roles)

Browse files

Files changed (1) hide show

tokenizer_config.json +2 -1

tokenizer_config.json CHANGED Viewed

@@ -41,5 +41,6 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<unk>"
 }

   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>",
+  "chat_template": "{%- macro flat(c) -%}{%- set f = namespace(o='') -%}{%- for line in (c or '').split('\n') -%}{%- set l = line.rstrip(' \t\r') -%}{%- if l -%}{%- if f.o and not l.startswith(' ') -%}{%- set f.o = f.o + ' ' + l -%}{%- else -%}{%- set f.o = f.o + l -%}{%- endif -%}{%- endif -%}{%- endfor -%}{{- f.o -}}{%- endmacro -%}{%- macro join(a, b) -%}{{- a + b if (not a or not b or b.startswith(' ')) else a + ' ' + b -}}{%- endmacro -%}{%- set msgs = (messages | rejectattr('role', 'equalto', 'system') | list)[-5:] -%}{%- set ns = namespace(out='') -%}{%- for m in msgs -%}{%- set ns.out = join(ns.out, flat(m['content'])) -%}{%- endfor -%}{{ ns.out }}"
 }